Title: A deep neural architecture for sentence semantic matching

Authors: Xu Zhang; Wenpeng Lu; Fangfang Li; Ruoyu Zhang; Jinyong Cheng

Addresses: School of Computer Science and Technology, Qilu University of Technology (Shandong Academy of Sciences), Jinan, Shandong, China ' School of Computer Science and Technology, Qilu University of Technology (Shandong Academy of Sciences), Jinan, Shandong, China ' oOh! Media, Sydney, NSW, Australia ' School of Computer Science and Technology, Qilu University of Technology (Shandong Academy of Sciences), Jinan, Shandong, China ' School of Computer Science and Technology, Qilu University of Technology (Shandong Academy of Sciences), Jinan, Shandong, China

Abstract: Sentence semantic matching (SSM) is a fundamental research task in natural language processing. Most existing SSM methods take the advantage of sentence representation learning to generate a single or multi-granularity semantic representation for sentence matching. However, sentence interactions and loss function which are the two key factors for SSM still have not been fully considered. Accordingly, we propose a deep neural network architecture for SSM task with a sentence interactive matching layer and an optimised loss function. Given two input sentences, our model first encodes them to embeddings with an ordinary long short-term memory (LSTM) encoder. Then, the encoded embeddings are handled by an attention layer to find the key and important words in the sentences. Next, sentence interactions are captured with a matching layer to output a matching vector. Finally, based on the matching vector, a fully connected multi-layer perceptron outputs the similarity score. The model also distinguishes the equivocation training instances with an improved optimised loss function. We also systematically evaluate our model on a public Chinese semantic matching corpus, BQ corpus. The results demonstrate that our model outperforms the state-of-the-art methods, i.e., BiMPM, DIIN.

Keywords: sentence matching; representation learning; sentence interaction; loss function; deep neural model; long short-term memory; LSTM.

DOI: 10.1504/IJCSE.2020.10028622

International Journal of Computational Science and Engineering, 2020 Vol.21 No.4, pp.574 - 582

Received: 28 Feb 2019
Accepted: 02 Apr 2019

Published online: 24 Apr 2020 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article